Initializing data... ...allocating CPU memory ...allocating GPU memory ...generating data Data length: 8388608; kernel length: 128 Running GPU dyadic convolution using Fast Walsh Transform... GPU time: 18.172001 ms; GOP/s: 15.925983 Reading back GPU results... Running straightforward CPU dyadic convolution... Comparing the results... L2 norm: NAN FAILED Shutting down... Press ENTER to exit...